• Decision trees have approximate fingerprints 

      Lavín Puente, Víctor Angel; Raghavan, Vijay (1996-04)
      Report de recerca
      Accés obert
      We prove that decision trees exhibit the "approximate fingerprint" property, and therefore are not polynomially learnable using only equivalence queries. A slight modification of the proof extends this result to ...
    • Learning monotone term decision lists 

      Guijarro Guillem, David; Lavín Puente, Víctor Angel; Raghavan, Vijay (1996-09)
      Report de recerca
      Accés obert
      We study the learnability of monotone term decision lists in the exact model of equivalence and membership queries. We show that, for any constant k>0, k-term monotone decision lists are exactly and properly learnable with ...
    • Learning nearly monotone k-term DNF 

      Castro Rabal, Jorge; Guijarro Guillem, David; Lavín Puente, Víctor Angel (1996-09)
      Report de recerca
      Accés obert
      This note studies the learnability of the class k-term DNF with a bounded number of negations per term. We study the case of learning with membership queries alone, and give tight upper and lower bounds on the ...
    • Monotone term decision lists 

      Guijarro Guillem, David; Lavín Puente, Víctor Angel; Raghavan, V (1998-11)
      Report de recerca
      Accés obert
      We introduce a new representation class of Boolean functions---monotone term decision lists---which combines compact representation size with tractability of essential operations. We present many properties of the class ...
    • The Query complexity of learning context-free grammars 

      Domingo Soriano, Carlos; Lavín Puente, Víctor Angel (1994-10)
      Report de recerca
      Accés obert
      In the COLT'94 Conference A. Burago showed that the class of structurally reversible grammars is learnable in polynomial time using membership and equivalence queries. The paper shows that this class of grammars is not ...